The desired width of the 95% confidence intervals (W) for the lowest sensitivity among existing search strategies was used to calculate the number of high-quality articles needed to reliably update search strategies.
The sample size calculation for the number of pass articles needed in a journal subset was based on the desired width of the 95% confidence intervals (W) around the sensitivity of the existing search strategies [ 16].
The results are presented in figures 1, 2, 3. Analysis of figure 1 indicates that the proposed 95% confidence interval for W approximates the desired coverage of 95% when W is between 0.5 and 1.
If a confidence interval for w j 2 was required then this could be obtained by modifying this procedure, so that the bootstrap replications were produced using the fitted RVSOM, and obtaining the confidence interval from the resulting distribution's percentiles.
Sample size estimation for the proportion estimates was based on the following assumption: For a desired width of a 95% confidence interval of w =.20, an alpha-level of p =.05, an intra-cluster correlation of r =.02 and a number of m = 30 clusters, the required number in each cluster was n = 3.5 which corresponds to an estimated sample size of 107.
Abbreviations: HR hazard ratio, CI confidence interval, %ECW BIA /TBW Watson percentage of extracellular water as measured by bioimpedance analysis to total body water calculated using the Watson formula, eGFR CKD-EPI estimated glomerular filtration rate using the Chronic Kidney Disease Epidemiology Collaboration equation, UPCR urinary protein-to-creatinine ratio.
Growth rate is zero at 13,131 W (95% confidence intervals, 10,590 21,150 W), meaning that under current conditions the global population would stop growing if everyone had access to ∼13 kW of energy, or over 150 times more than basal metabolic rate [21].
Interactions between overlapping gap genes are mostly weakly repressive or absent, and are largely consistent with Figure 4(a): confidence intervals for W h b K r, W K r h b, W K r k n i, W g t h b, and W g t k n i indicate no interaction, while confidence intervals for W k n i g t, and W k n i K r suggest the absence of activation.
In the same study, the observation that PFGE type could predict emm type to a greater extent than the reverse is supported by non-overlapping 95% confidence intervals of W (0.95 [0.93–0.97] vs. 0.80 [0.80–0.80]).
For instance, Figure 5(a) shows the confidence intervals for W h b K r.
Finally, confidence intervals for W h b g t indicate the absence of repression.
